How to generate score.npy file
AnastasiaBam opened this issue · comments
Using the provided datasets i am facing an issue regarding the regressor training. I have trained the model but i don't understand how the scores.npy file is generated
scores.npy contain ground truth quality scores usually available in any public IQA datasets. This is only required to train the regressor in order to predict quality.
score.npy 包含通常在任何公共 IQA 数据集中可用的基本事实质量分数。这只需要训练回归器以预测质量。
Can you share your score.npy file in this repository? So that we can measure the SROCC and reproduce the results of your paper. Thank you very much!
As mentioned in my previous comments scores.npy depends on which public IQA dataset you're employing. Since I don't own those datasets, I cannot share them here. You need to download respective IQA datasets and use the ground truth opinion scores available in them in scores.npy file.